Knowledge catalogue
arXiv:2605.22168v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) map complex visual inputs to semantic spaces, but interpreting the cross-modal reasoning of VLMs currently relies on pos
arXiv:2506.16659v3 Announce Type: replace Abstract: Training large language models (LLMs) relies on adaptive optimizers such as Adam, which introduce extra operations and require significantly more me
arXiv:2605.21768v1 Announce Type: new Abstract: Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, updating, and reusing information across sessions.
arXiv:2605.21751v1 Announce Type: new Abstract: Text-to-optimization requires two separable capabilities: modeling -- choosing the right optimization structure -- and binding -- grounding every coeffi
arXiv:2602.13372v2 Announce Type: replace-cross Abstract: Evaluating moral alignment in agents navigating conflicting, hierarchically structured human norms is a critical challenge at the intersection
oh even better, since you can test the runtime without an LLM, you can post this into Claude: “look up http://activegraph.ai, install and run a small experiment I would like leveraging this, and expla
arXiv:2602.12506v3 Announce Type: replace Abstract: Reinforcement learning (RL) finetuning has become a key technique for enhancing large language models (LLMs) on reasoning-intensive tasks, motivatin
arXiv:2605.22297v1 Announce Type: new Abstract: Learning rate configuration is a fundamental aspect of modern deep learning. The prevailing practice of applying a uniform learning rate across all laye
arXiv:2605.22691v1 Announce Type: new Abstract: We show that posterior collapse in eta-VAEs implements automatic spectral pruning. A latent mode collapses if its contribution to reconstruction is belo
arXiv:2602.22270v2 Announce Type: replace Abstract: Spatio-temporal epidemic forecasting is critical for public health management, yet existing methods often struggle with insensitivity to weak epidem
arXiv:2605.21522v1 Announce Type: cross Abstract: Protein-protein interactions (PPIs) govern nearly all cellular processes, yet computational methods for identifying binding partners typically produce
arXiv:2605.21543v1 Announce Type: new Abstract: Benchmark data contamination has become a central challenge in LLM evaluation: when evaluation examples appear in the training data of one or more audit
arXiv:2605.21975v1 Announce Type: new Abstract: Financial markets are characterized by extreme non-stationarity, low signal-to-noise ratios, and strong dependence on external information such as news,
arXiv:2605.21692v1 Announce Type: new Abstract: Characterizing precisely the asymptotic generalization error of neural networks using parameters that can be estimated efficiently is a crucial problem
arXiv:2604.02889v2 Announce Type: replace-cross Abstract: Data assimilation is the process of estimating the state of a dynamical system over time by combining model predictions with measurements. Thi
arXiv:2602.07340v2 Announce Type: replace Abstract: Safety alignment of large language models remains brittle under domain shift and noisy preference supervision. Most existing robust alignment method
arXiv:2605.22083v1 Announce Type: cross Abstract: While flow-matching text-to-speech (TTS) achieves strong zero-shot speaker similarity and naturalness, it remains susceptible to content fidelity issu
arXiv:2603.21610v2 Announce Type: replace Abstract: Compliance monitoring in rule-governed domains (tax administration, clinical protocol adherence, environmental regulation) faces three structural ob
RWKV-7 G1g is here: the world's best pure RNN LLM, and a competitive LLM in general. Try https://huggingface.co/spaces/BlinkDL/RWKV-Gradio-2 for bsz16 7B inference. G1h in June 🙂 p.s. const 15000+tps
arXiv:2605.21557v1 Announce Type: cross Abstract: Conventional wisdom holds that large-batch training is fundamentally incompatible with Reinforcement Learning (RL) - beyond a modest threshold, increa
arXiv:2605.22112v1 Announce Type: cross Abstract: We present a framework for detecting transient gamma-ray phenomena in a controlled environment by combining end-to-end simulations of the Fermi-LAT sk
arXiv:2605.22743v1 Announce Type: new Abstract: Parameter-efficient fine-tuning enables fast personalization of text-to-image diffusion models, but composing multiple custom concepts remains challengi
Shipper’s “After Automation” is the best framing I’ve read of why AI keeps generating more work, not less. The line that stuck with me: the frame is not the framer. Models climb whatever benchmark we
arXiv:2605.22142v1 Announce Type: new Abstract: Reinforcement learning under partial observability requires deciding what information to retain, yet most memory-based approaches do not explicitly mode
arXiv:2605.22162v1 Announce Type: cross Abstract: Stellar spectra encode key information on the physical properties and chemical compositions of stars. Accurate stellar parameter determination is esse
arXiv:2605.22529v1 Announce Type: new Abstract: This paper investigates a unexplored yet impactful vulnerability in AI explainability used in intrusion detection (IDS): multicollinearity-induced insta
arXiv:2605.21813v1 Announce Type: new Abstract: Discrete probability laws underpin statistical modeling, yet the catalog of interpretable distributions has expanded only gradually through centuries of
arXiv:2605.21544v1 Announce Type: new Abstract: Near-infrared spectroscopy is increasingly used as a rapid, non-destructive chemical sensing technology for the analysis of food, pharmaceutical, biolog
The case against me below is completely intellectually dishonest, filled with lies and misrepresentations, wrong about almost literally everything it says—a textbook example of propaganda: - I didn’t
arXiv:2605.21856v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated impressive reasoning abilities across a wide range of tasks, but data contamination undermines the object
arXiv:2605.22653v1 Announce Type: cross Abstract: In learning-augmented online algorithms, predictions are usually valued for what they say: a value estimate, a solution, or an algorithmic recommendat
arXiv:2603.04525v2 Announce Type: replace-cross Abstract: Modern approaches for learning from non-Markovian time series, such as recurrent neural networks, neural controlled differential equations or
this has been my experience as well. there definitely were improvements, specifically wrt shell based computer use, but also regressions, especially in the last 3 version bumps of flicker and gerperte
this is even easier oh even better, since you can test the runtime without an LLM, you can post this into Claude: “look up http://activegraph.ai, install and run a small experiment I would like levera
Nemotron-Labs Diffusion Language Models represent NVIDIA's approach to achieving faster text generation through diffusion-based architectures, potentially offering significant speed improvements over
arXiv:2605.21805v1 Announce Type: cross Abstract: State-space models (SSMs) are powerful probabilistic tools for modeling time-varying systems with latent dynamics. Inference in SSMs involves the esti
arXiv:2605.22621v1 Announce Type: cross Abstract: The detection of previously unseen network attacks remains a major challenge for intrusion detection systems. Although supervised learning methods oft
arXiv:2605.22368v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed for software engineering, constructing high-quality benchmarks is crucial for evaluating not j
arXiv:2605.21606v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) trains a student on its own rollouts using a privileged teacher, but its standard objective weights all generated tok
arXiv:2605.22644v1 Announce Type: new Abstract: Stochastic Gradient Descent (SGD) is commonly modeled as a Langevin process, assuming that minibatch noise acts as Brownian motion. However, this approx
This is a Wordle game result post from Anthropic's X (Twitter) account showing the solution found in 5 of 6 attempts, with the color-coded emoji grid indicating which letters were correct, misplaced,
arXiv:2605.22328v1 Announce Type: new Abstract: Land Use Land Cover (LULC) classification is essential for national 3D mapping, geospatial analysis, and sustainable planning. Multispectral (MS) LiDAR
arXiv:2605.22099v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for grounding large language model (LLM) outputs in retrieved evidence, thereby
arXiv:2605.21500v1 Announce Type: cross Abstract: Event cameras have emerged as a high-bandwidth, low-latency sensing modality for safety-critical perception in automated driving systems (ADS), offeri
arXiv:2605.22126v1 Announce Type: new Abstract: In everyday photography, aesthetically appealing moments are often captured with structural flaws (e.g., composition, camera viewpoint, or pose) that ex
arXiv:2605.20425v1 Announce Type: new Abstract: Designing multi-agent workflows is especially difficult in open-ended scientific settings where tasks lack curated training sets, reliable scalar evalua
arXiv:2605.22366v1 Announce Type: new Abstract: Agricultural decision-making increasingly requires multimodal systems that can transform visual observations into reliable, executable actions. However,
arXiv:2605.22034v1 Announce Type: new Abstract: Visual grounding, the task of localizing objects described by natural-language expressions, is a foundational capability for agricultural AI systems, en
arXiv:2512.20538v2 Announce Type: replace Abstract: Single-view RGB model-based object pose estimation methods achieve strong generalization but are fundamentally limited by depth ambiguity, clutter,
arXiv:2605.22714v1 Announce Type: cross Abstract: Large language models are routinely used as automated evaluators: to review code, moderate content, or score outputs, often with many items passing th
Anthropic: Anthropic says Claude Mythos Preview has been used to find more than 10,000 high- or critical-severity vulnerabilities since the launch of Project Glasswing — Last month, we launched Projec
arXiv:2605.22081v1 Announce Type: new Abstract: We present ArabDiscrim, a decade-long lexical resource and corpus of 293K public Arabic Facebook posts (2014--2024) discussing racism and discrimination
arXiv:2605.22204v1 Announce Type: new Abstract: This paper presents the Arabic Women and Society Corpus, a ten year collection of 252,487 public Arabic Facebook posts related to women's empowerment an
arXiv:2605.21728v1 Announce Type: cross Abstract: Image captioning evaluation remains a significant challenge, as vision-language models evolve toward more challenging capabilities such as generating
arXiv:2605.22732v1 Announce Type: cross Abstract: We investigate whether acoustic emotion recognition models can serve as proxies for the Pathos dimension in political speech analysis, as operationali
arXiv:2603.14987v2 Announce Type: replace Abstract: Agentic AI systems increasingly act through tool-augmented, multi-step workflows whose failures (unsafe tool use, unauthorised actions, social harm)
arXiv:2605.22578v1 Announce Type: new Abstract: Online map estimation is a crucial component of autonomous driving systems that reduces the reliance on costly high-definition maps. State-of-the-art (S
arXiv:2605.22164v1 Announce Type: cross Abstract: Latent world models can contain the state needed for control, yet their terminal-cost interface can expose the planner to the wrong decision-relevant
arXiv:2605.22579v1 Announce Type: new Abstract: Recent work has identified a counterintuitive phenomenon termed 'Hyperfitting', where fine-tuning Large Language Models (LLMs) to near-zero training los
Big fan of teaching more people the basics of using Claude Code in an accessible way. So much of the world has not yet used agents. There's a lot of opportunity to level the playing field and expand a